Researches using margin based comparison loss demonstrate the effectiveness of penalizing the distance between face feature and their corresponding class centers. Despite their popularity and excellent performance, they do not explicitly encourage the generic embedding learning for an open set recognition problem. In this paper, we analyse margin based softmax loss in probability view. With this perspective, we propose two general principles: 1) monotonic decreasing and 2) margin probability penalty, for designing new margin loss functions. Unlike methods optimized with single comparison metric, we provide a new perspective to treat open set face recognition as a problem of information transmission. And the generalization capability for face embedding is gained with more clean information. An auto-encoder architecture called Linear-Auto-TS-Encoder(LATSE) is proposed to corroborate this finding. Extensive experiments on several benchmarks demonstrate that LATSE help face embedding to gain more generalization capability and it boosted the single model performance with open training dataset to more than $99\%$ on MegaFace test.
Recently, two-dimensional canonical correlation analysis (2DCCA) has been successfully applied for image feature extraction. The method instead of concatenating the columns of the images to the one-dimensional vectors, directly works with two-dimensional image matrices. Although 2DCCA works well in different recognition tasks, it lacks a probabilistic interpretation. In this paper, we present a probabilistic framework for 2DCCA called probabilistic 2DCCA (P2DCCA) and an iterative EM based algorithm for optimizing the parameters. Experimental results on synthetic and real data demonstrate super…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；University of Toronto（多伦多大学）
Analyzing the story behind TV series and movies often requires understanding who the characters are and what they are doing. With improving deep face models, this may seem like a solved problem. However, as face detectors get better, clustering/identification needs to be revisited to address increasing diversity in facial appearance. In this paper, we address video face clustering using unsupervised methods. Our emphasis is on distilling the essential information, identity, from the representations obtained using deep pre-trained face networks. We propose a self-supervised Siamese network that…
Embedding methods have achieved success in face recognition by comparing facial features in a latent semantic space. However, in a fully unconstrained face setting, the facial features learned by the embedding model could be ambiguous or may not even be present in the input face, leading to noisy representations. We propose Probabilistic Face Embeddings (PFEs), which represent each face image as a Gaussian distribution in the latent space. The mean of the distribution estimates the most likely feature values while the variance shows the uncertainty in the feature values. Probabilistic solution…
National University of Singapore（新加坡国立大学）；Youtu Lab Tencent（腾讯优图实验室）
This paper proposes a probabilistic contrastive loss function for self-supervised learning. The well-known contrastive loss is deterministic and involves a temperature hyperparameter that scales the inner product between two normed feature embeddings. By reinterpreting the temperature hyperparameter as a quantity related to the radius of the hypersphere, we derive a new loss function that involves a confidence measure which quantifies uncertainty in a mathematically grounding manner. Some intriguing properties of the proposed loss function are empirically demonstrated, which agree with human-l…
Face recognition in unconstrained environments is challenging due to variations in illumination, quality of sensing, motion blur and etc. An individual's face appearance can vary drastically under different conditions creating a gap between train (source) and varying test (target) data. The domain gap could cause decreased performance levels in direct knowledge transfer from source to target. Despite fine-tuning with domain specific data could be an effective solution, collecting and annotating data for all domains is extremely expensive. To this end, we propose a self-supervised domain learni…
We present a novel face reconstruction method capable of reconstructing detailed face geometry, spatially varying face reflectance from a single monocular image. We build our work upon the recent advances of DNN-based auto-encoders with differentiable ray tracing image formation, trained in self-supervised manner. While providing the advantage of learning-based approaches and real-time reconstruction, the latter methods lacked fidelity. In this work, we achieve, for the first time, high fidelity face reconstruction using self-supervised learning only. Our novel coarse-to-fine deep architecture…
Nitte Meenakshi Institute of Technology（尼特·米纳克希理工学院）
It is human nature to give prime importance to facial appearances. Often, to look good is to feel good. Also, facial features are unique to every individual on this planet, which means it is a source of vital information. This work proposes a framework named E-Pro for the detection and recognition of faces by taking facial images as inputs. E-Pro has its potential application in various domains, namely attendance, surveillance, crowd monitoring, biometric-based authentication etc. E-Pro is developed here as a mobile application that aims to aid lecturers to mark attendance in a classroom by de…
Probabilistic Face Embeddings (PFE) can improve face recognition performance in unconstrained scenarios by integrating data uncertainty into the feature representation. However, existing PFE methods tend to be over-confident in estimating uncertainty and is too slow to apply to large-scale face matching. This paper proposes a regularized probabilistic face embedding method to improve the robustness and speed of PFE. Specifically, the mutual likelihood score (MLS) metric used in PFE is simplified to speedup the matching of face feature pairs. Then, an output-constraint loss is proposed to penal…
PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation
School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；Intelligent Game and Decision Laboratory（智能游戏与决策实验室）；Alibaba DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；Zhejiang University（浙江大学）
Prevailing defense mechanisms against adversarial face images tend to overfit to the adversarial perturbations in the training set and fail to generalize to unseen adversarial attacks. We propose a new self-supervised adversarial defense framework, namely FaceGuard, that can automatically detect, localize, and purify a wide variety of adversarial faces without utilizing pre-computed adversarial training samples. During training, FaceGuard automatically synthesizes challenging and diverse adversarial attacks, enabling a classifier to learn to distinguish them from real faces and a purifier atte…
East China Normal University（华东师范大学）；Deakin University（迪肯大学）
Face spoofing causes severe security threats in face recognition systems. Previous anti-spoofing works focused on supervised techniques, typically with either binary or auxiliary supervision. Most of them suffer from limited robustness and generalization, especially in the cross-dataset setting. In this paper, we propose a semi-supervised adversarial learning framework for spoof face detection, which largely relaxes the supervision condition. To capture the underlying structure of live faces data in latent representation space, we propose to train the live face data only, with a convolutional …
Toyota Motor Europe（丰田汽车欧洲公司）；Czech Technical University in Prague（捷克布拉格技术大学）
Cross entropy loss has served as the main objective function for classification-based tasks. Widely deployed for learning neural network classifiers, it shows both effectiveness and a probabilistic interpretation. Recently, after the success of self supervised contrastive representation learning methods, supervised contrastive methods have been proposed to learn representations and have shown superior and more robust performance, compared to solely training with cross entropy loss. However, cross entropy loss is still needed to train the final classification layer. In this work, we investigate…
Labeling training examples at scale is a perennial challenge in machine learning. Self-supervision methods compensate for the lack of direct supervision by leveraging prior knowledge to automatically generate noisy labeled examples. Deep probabilistic logic (DPL) is a unifying framework for self-supervised learning that represents unknown labels as latent variables and incorporates diverse self-supervision using probabilistic logic to train a deep neural network end-to-end using variational EM. While DPL is successful at combining pre-specified self-supervision, manually crafting self-supervis…
Balancing computational efficiency with recognition accuracy is one of the major challenges in real-world video-based face recognition. A significant design decision for any such system is whether to process and use all possible faces detected over the video frames, or whether to select only a few "best" faces. This paper presents a video face recognition system based on probabilistic Multi-Region Histograms to characterise performance trade-offs in: (i) selecting a subset of faces compared to using all faces, and (ii) combining information from all faces via clustering. Three face selection m…
InterDigital R&I（InterDigital研究与创研中心）；Max-Planck-Institute for Informatics（马克斯·普朗克信息学研究所）
Robust face reconstruction from monocular image in general lighting conditions is challenging. Methods combining deep neural network encoders with differentiable rendering have opened up the path for very fast monocular reconstruction of geometry, lighting and reflectance. They can also be trained in self-supervised manner for increased robustness and better generalization. However, their differentiable rasterization based image formation models, as well as underlying scene parameterization, limit them to Lambertian face reflectance and to poor shape details. More recently, ray tracing was int…
This paper proposes a novel face recognition algorithm based on large-scale supervised hierarchical feature learning. The approach consists of two parts: hierarchical feature learning and large-scale model learning. The hierarchical feature learning searches feature in three levels of granularity in a supervised way. First, face images are modeled by receptive field theory, and the representation is an image with many channels of Gaussian receptive maps. We activate a few most distinguish channels by supervised learning. Second, the face image is further represented by patches of picked channe…
In this paper, we propose self-supervised speaker representation learning strategies, which comprise of a bootstrap equilibrium speaker representation learning in the front-end and an uncertainty-aware probabilistic speaker embedding training in the back-end. In the front-end stage, we learn the speaker representations via the bootstrap training scheme with the uniformity regularization term. In the back-end stage, the probabilistic speaker embeddings are estimated by maximizing the mutual likelihood score between the speech samples belonging to the same speaker, which provide not only speaker…
Microsoft Research（微软研究院）；JD Finance America Corporation（京东金融美国公司）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）
Deep learning has proven effective for various application tasks, but its applicability is limited by the reliance on annotated examples. Self-supervised learning has emerged as a promising direction to alleviate the supervision bottleneck, but existing work focuses on leveraging co-occurrences in unlabeled data for task-agnostic representation learning, as exemplified by masked language model pretraining. In this chapter, we explore task-specific self-supervision, which leverages domain knowledge to automatically annotate noisy training examples for end applications, either by introducing lab…
Although deep convolutional networks have achieved great performance in face recognition tasks, the challenge of domain discrepancy still exists in real world applications. Lack of domain coverage of training data (source domain) makes the learned models degenerate in a testing scenario (target domain). In face recognition tasks, classes in two domains are usually different, so classical domain adaptation approaches, assuming there are shared classes in domains, may not be reasonable solutions for this problem. In this paper, self-supervised learning is adopted to learn a better embedding spac…
Australian National University（澳大利亚国立大学）；JD AI Research（京东人工智能研究院）；Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Although deep face recognition benefits significantly from large-scale training data, a current bottleneck is the labelling cost. A feasible solution to this problem is semi-supervised learning, exploiting a small portion of labelled data and large amounts of unlabelled data. The major challenge, however, is the accumulated label errors through auto-labelling, compromising the training. This paper presents an effective solution to semi-supervised face recognition that is robust to the label noise aroused by the auto-labelling. Specifically, we introduce a multi-agent method, named GroupNet (GN…
Landmark detection algorithms trained on high resolution images perform poorly on datasets containing low resolution images. This deters the performance of algorithms relying on quality landmarks, for example, face recognition. To the best of our knowledge, there does not exist any dataset consisting of low resolution face images along with their annotated landmarks, making supervised training infeasible. In this paper, we present a semi-supervised approach to predict landmarks on low resolution images by learning them from labeled high resolution images. The objective of this work is to show …
University of Waterloo（滑铁卢大学）；Vector Institute（向量研究所）
In this paper, we present a new algorithm for semi-supervised representation learning. In this algorithm, we first find a vector representation for the labels of the data points based on their local positions in the space. Then, we map the data to lower-dimensional space using a linear transformation such that the dependency between the transformed data and the assigned labels is maximized. In fact, we try to find a mapping that is as discriminative as possible. The approach will use Hilber-Schmidt Independence Criterion (HSIC) as the dependence measure. We also present a kernelized version of…
Center for Machine Vision and Signal Analysis（机器视觉与信号分析中心）；University of Oulu（奥卢大学）
Face presentation attack detection (PAD) plays an important role in defending face recognition systems against presentation attacks. The success of PAD largely relies on supervised learning that requires a huge number of labeled data, which is especially challenging for videos and often requires expert knowledge. To avoid the costly collection of labeled data, this paper presents a novel method for self-supervised video representation learning via motion prediction. To achieve this, we exploit the temporal consistency based on three RGB frames which are acquired at three different times in the…
Bridging the Gaps: Utilizing Unlabeled Face Recognition Datasets to Boost Semi-Supervised Facial Expression Recognition
West China Hospital, Sichuan University（四川大学华西医院）；Institutes for Systems Genetics（系统遗传学研究所）；Frontiers Science Center for Disease-related Molecular Network（疾病相关分子网络前沿科学中心）
Wuhan University（武汉大学）；Tencent AI Laboratory（腾讯AI实验室）；University of California at Los Angeles（加利福尼亚大学洛杉矶分校）；Johns Hopkins University（约翰斯·霍普金斯大学）
This paper addresses the problem of face recognition when there is only few, or even only a single, labeled examples of the face that we wish to recognize. Moreover, these examples are typically corrupted by nuisance variables, both linear (i.e., additive nuisance variables such as bad lighting, wearing of glasses) and non-linear (i.e., non-additive pixel-wise nuisance variables such as expression changes). The small number of labeled examples means that it is hard to remove these nuisance variables between the training and testing faces to obtain good recognition performance. To address the p…
Kuaishou Technology（快手科技）；University of Oulu（奥卢大学）；Communication University of China（中国传媒大学）；Academy of Sciences, Mininglamp Technology（明略科技集团科学院）；CBSR&NLPR, CASIA（中国科学院自动化研究所）；Lappeenranta-Lahti University of Technology（拉彭兰塔-拉赫蒂理工大学）
Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems. Empirically, given an image, a model with more consistent output on different views of this image usually performs better, as shown in Fig.1. Motivated by this exciting observation, we conjecture that encouraging feature consistency of different views may be a promising way to boost FAS models. In this paper, we explore this way thoroughly by enhancing both Embedding-level and Prediction-level Consistency Regularization (EPCR) in FAS. Specifically, at the embedding-level, we design a dense similarity loss to ma…
One of the key issues in facial expression recognition in the wild (FER-W) is that curating large-scale labeled facial images is challenging due to the inherent complexity and ambiguity of facial images. Therefore, in this paper, we propose a self-supervised simple facial landmark encoding (SimFLE) method that can learn effective encoding of facial landmarks, which are important features for improving the performance of FER-W, without expensive labels. Specifically, we introduce novel FaceMAE module for this purpose. FaceMAE reconstructs masked facial images with elaborately designed semantic …
Indian Institute of Science（印度科学学院）；National Institute of Technology（国家技术学院）
Facial recognition has always been a challeng- ing task for computer vision scientists and experts. Despite complexities arising due to variations in camera parameters, illumination and face orientations, significant progress has been made in the field with deep learning algorithms now competing with human-level accuracy. But in contrast to the recent advances in face recognition techniques, Disguised Facial Identification continues to be a tougher challenge in the field of computer vision. The modern day scenario, where security is of prime concern, regular face identification techniques do n…
The performance of many machine learning techniques depends on the choice of an appropriate similarity or distance measure on the input space. Similarity learning (or metric learning) aims at building such a measure from training data so that observations with the same (resp. different) label are as close (resp. far) as possible. In this paper, similarity learning is investigated from the perspective of pairwise bipartite ranking, where the goal is to rank the elements of a database by decreasing order of the probability that they share the same label with some query data point, based on the s…
Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形研究所）；TU Darmstadt（达姆施塔特工业大学）
It is challenging to derive explainability for unsupervised or statistical-based face image quality assessment (FIQA) methods. In this work, we propose a novel set of explainability tools to derive reasoning for different FIQA decisions and their face recognition (FR) performance implications. We avoid limiting the deployment of our tools to certain FIQA methods by basing our analyses on the behavior of FR models when processing samples with different FIQA decisions. This leads to explainability tools that can be applied for any FIQA method with any CNN-based FR solution using activation mappi…
Autonomous systems require a continuous and dependable environment perception for navigation and decision-making, which is best achieved by combining different sensor types. Radar continues to function robustly in compromised circumstances in which cameras become impaired, guaranteeing a steady inflow of information. Yet, camera images provide a more intuitive and readily applicable impression of the world. This work combines the complementary strengths of both sensor types in a unique self-learning fusion approach for a probabilistic scene reconstruction in adverse surrounding conditions. Aft…
University Hospital of Strasbourg（斯特拉斯堡大学医院）；University of Strasbourg（斯特拉斯堡大学）；CNRS（法国国家科学研究中心）；IHU Strasbourg（斯特拉斯堡大学医院研究所）
Purpose: Face detection is a needed component for the automatic analysis and assistance of human activities during surgical procedures. Efficient face detection algorithms can indeed help to detect and identify the persons present in the room, and also be used to automatically anonymize the data. However, current algorithms trained on natural images do not generalize well to the operating room (OR) images. In this work, we provide a comparison of state-of-the-art face detectors on OR data and also present an approach to train a face detector for the OR by exploiting non-annotated OR images. Me…
DifFIQA: Face Image Quality Assessment Using Denoising Diffusion Probabilistic Models
University of Ljubljana, Faculty of Electrical Engineering（卢布尔雅那大学电气工程学院）；University of Ljubljana, Faculty of Computer and Information Science（卢布尔雅那大学计算机与信息科学学院）
The seeded Watershed algorithm / minimax semi-supervised learning on a graph computes a minimum spanning forest which connects every pixel / unlabeled node to a seed / labeled node. We propose instead to consider all possible spanning forests and calculate, for every node, the probability of sampling a forest connecting a certain seed with that node. We dub this approach "Probabilistic Watershed". Leo Grady (2006) already noted its equivalence to the Random Walker / Harmonic energy minimization. We here give a simpler proof of this equivalence and establish the computational feasibility of the…
NICTA（澳大利亚国家信息与通信技术研究院）；The University of Queensland（昆士兰大学）
In video based face recognition, face images are typically captured over multiple frames in uncontrolled conditions, where head pose, illumination, shadowing, motion blur and focus change over the sequence. Additionally, inaccuracies in face localisation can also introduce scale and alignment variations. Using all face images, including images of poor quality, can actually degrade face recognition performance. While one solution it to use only the "best" subset of images, current face selection techniques are incapable of simultaneously handling all of the abovementioned issues. We propose an …
